Required Senior AI Engineer - Applied AI Engineering Group
The Dream Job
It starts with you - an engineer driven to build the agentic AI platform that turns LLMs into reliable, production-grade capabilities. You care about clean APIs, well-defined service boundaries, and systems that teams can build on with confidence. Dream is AI-first across the board - every team builds and operates agents. You'll architect and ship the platform that makes this possible: agent orchestration frameworks, LLM gateways, evaluation pipelines, tool-calling infrastructure, and retrieval systems. Without this platform, agents don't ship - you own the layer that turns AI research into Sovereign AI products, deployed across cloud and on-prem environments.
If you want to make a meaningful impact, join our mission and build the agentic AI platform that drives Sovereign AI products - this role is for you.
The Dream-Maker Responsibilities
Design and build agentic systems - single and multi-agent workflows with planning, memory, context engineering, and tool use - for both internal automation and product-facing autonomous capabilities operating over long time horizons.
Build and operate the AI platform layer - LLM gateways, prompt management, structured output handling, tool-calling infrastructure, and cost/latency optimization - deployed on Kubernetes, consumed by every team for their agentic work.
Own the agent framework layer - orchestration primitives, execution environments, state management, and sandboxed tool execution - giving every team the building blocks to create and operate their own agents.
Build evaluation infrastructure that gives teams confidence in agent behavior - automated LLM and agent evals for quality, correctness, safety, latency, cost, and regressions, including human-in-the-loop oversight for mission-critical workflows.
Productionize and harden backend services (APIs, gRPC, async workers) that integrate LLMs - with proper error handling, retries, circuit breakers, and high-availability patterns.
Own RAG pipelines and retrieval systems - indexing, chunking, embedding, vector database management, filtering, and relevance tuning for production retrieval.
Optimize performance and cost across the AI stack - model routing, caching, batching, and inference cost management.
Ship shared tooling - libraries, SDKs, agent templates, and documentation - while working closely with ML Platform, Data Platform, DevOps, and other teams across the Applied AI Engineering group. Own architecture, documentation, and operations end-to-end.
דרישות:
5+ years in backend or distributed systems engineering, with 2+ years focused on production systems that integrate AI/ML models or LLMs.
Engineering craft - Strong Python, Go, or Java, system architecture, API design, testing, and secure coding practices.
Agentic systems - Experience designing and building agent orchestration, tool-use systems, and autonomous workflows; familiarity with frameworks like LangGraph or similar, or having built equivalent from scratch
Backend engineering - Experience building production APIs and services (FastAPI or similar); async programming, service architecture, high-availability, and reliability patterns (retries, circuit breakers, backpressure)
LLM integration - Hands-on experience integrating LLMs via SDKs and APIs; context engineering, structured outputs, tool calling, and model routing
RAG & retrieval - Experience with embedding pipelines, vector databases (e.g., Milvus, Qdrant, Pinecone), chunking strategies, and relevance tuning
Evaluation & observability - Experience designing LLM and agent evals, monitoring AI system quality, and building observability for non-deterministic systems
Nice to Have:
Platform & infra - Kubernetes, AWS, Terraform or similar IaC, CI/CD, container orchestration, deploying and operating production services
Experience with MCP or similar tool-use protocols for agent-to-service communication
Hands-on ML experience - המשרה מיועדת לנשים ולגברים כאחד.